Finding Similar Products in E-commerce Sites Based on Attributes

We present a preliminary study on the problem of finding products similar to a product given as input, based solely on their attributes. We assume that we are given a set of products from a same category of a same on-line store, were each product is described in a catalog by a number of attributes (e.g., general characteristics, technical specifications, etc.). This problem, which at a first glance may be seen as straightforward or even mundane, is in fact challenging and intriguing. In fact, any automatic solution for it requires techniques for comparing tens of different atributes, whose semantics are often very technical and specific (e.g., the shutter speed of a camera) and also requires dealing with hundreds of products in the category. To be generic, such a solution must also deal with several distinct product categories. In here, we describe and evaluate a similarity function we have proposed for comparing products based on their attributes. This function uses a number of attribute-specific similarity functions, which are selected according to a class assigned to the attribute. The assignment of classes to attributes is carried out by a simple classification strategy, which we also describe and evaluate. Experiments we carried out to evaluate our proposed similarity function using data from real catalogs in five distinct popular product categories have shown promising results.